"Servers Offering MCP Prompts as Prompt Primitives" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Engram is a persistent, long-term memory layer for AI agents and assistants. Claude, ChatGPT, Grok, Cursor and any MCP client share one memory, stored as plain markdown notes: your knowledge base, second brain and AI context in one place. No extraction step: the memory is the note itself, so you can read exactly what your AI remembers and fix it. Edit your memory in Obsidian (real-time sync), the web app, or on your phone. Hybrid keyword + semantic search (RAG over your notes) finds exact strings like error messages, config keys and IDs. Remote MCP server over Streamable HTTP with OAuth 2.1; notes encrypted at rest. Https://engram.page https://youtu.be/rwnPeZ-8Lqo?is=NI-N7BduydGAiZlF https://github.com/engram-app/Engram
jitprompt gives your agents just-in-time instructions. Upload your docs as they are, and your agent gets the right section over MCP at the moment it needs it, instead of 20k tokens of system prompt every turn.
Turn URLs, PDFs and DOCX into clean Markdown for agents, plus prompt-injection scanning
Web pages, PDFs and search results as LLM-ready Markdown or chunks. Firecrawl-compatible, EU-hosted.
Search and fetch vibe-coding Agent Skills (SKILL.md files) and prompts from TheSkillVault library.
Compress, merge, split, convert, OCR, redact, sign and create PDFs, and ask questions about them, without leaving the chat. Sign in with a FynePDF account (OAuth) or use an API key; results come back as files you can download or keep.
Serve a folder of Markdown notes as an MCP server: hybrid search, reading, and sourced answers.
Search and load AI datasets, prompts and few-shot contexts from the ContexteTech catalogue.
The world's first named AI prompt quality score. Score, optimize, and compare LLM prompts before they hit any model. Free tier available. Built on PEEM, RAGAS, G-Eval, and MT-Bench frameworks. x402-native on Base.
graphrag-ts is a TypeScript GraphRAG engine on PostgreSQL/pgvector, served as a Streamable HTTP MCP endpoint. Public read tier needs no credentials (20 req/min per IP): integrity_paper_status, retraction_propagation, integrity_evidence_audit. A bearer key unlocks graph query, global map-reduce, index jobs and memory writes. Free browser demo: https://huggingface.co/spaces/ashesborn6/retraction-status
Full-text financial reports (US, China, Japan, Korea, Taiwan, UK) as clean Markdown for RAG agents.
Unstructured document processing for LLM pipelines. Upload as PDF/DOCX/TXT any supported files, extract structured data (PII-redacted), build LLM-ready datasets, and search/export results — all via MCP tools (document.process, job.status, job.result, dataset.build, dataset.search, dataset.export).
Your curated sources (RSS, YouTube, podcasts, Google News) as context for any AI agent.
MCP server providing AI security tools: prompt injection detection, PII scanning, and RAG input validation. Works with Claude, Cursor, and any MCP-compatible client.
Parse PDF/Word/PPT/HTML to Markdown; tables as JSON, image extraction, RAG chunking, page ranges.
Hand-picked landing pages as design references for your agent: design systems, motion, sections.
The context layer for the physical world: filmed spaces as cited context for agents.
Rafter holds a team's durable knowledge — skills, agents and memory files, each versioned — and serves it to AI tools over MCP. Agents search across the team's artifacts before answering questions about how the team works or what was decided, fetch full artifact text along with its citation edges (cites, cited_by, links) to explore related material, and write new learnings back as memory. Also covers workspace, team and membership management.
Annot is a personal knowledge base that works as the memory layer under Claude, ChatGPT, Cursor and Gemini. Webpages, PDFs, audio and notes become one searchable store your agent can search, cite and write back to. Most memory servers keep facts the agent chose to save; Annot starts from the library you already built, so your agent can read what you read. 29 tools: search, context loading, write-back, topics, export. Annot account required (invite-only beta).
ContextBook is an open-source MCP server that gives AI tools a persistent, searchable context library. Store information as Books and Pages, retrieve exactly what's needed via natural-language semantic search - injected on demand, not pre-loaded. Works with Cursor, Claude, Windsurf, and any MCP-compatible client. Self-hostable, MIT licensed.
RAG-as-a-service MCP sunucusu — çok-kiracılı koleksiyon yönetimi, metin ingest (chunk+embed+upsert,…
Web search, scraping, RAG answers with citations, and translation as MCP tools.
Illumora Craft — evidence-augmented prompt compile for agents via remote MCP (OAuth) or local stdio.
Manage, version, and publish LLM prompts with blocks, variables, and evaluations.
